cve.bz

CVE-2026-103241 vllm vllm: Improper Resource Shutdown or Release

5.5 mediumEPSS 0.7%Fix available

Medium (5.5) in vllm vllm. EPSS 0.7% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.27.0.

On this page
A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has been published and may be used. Upgrading to version 0.29.1rc0 is able to resolve this issue. This patch is called 3439bad37e68ba9755a46f4f6b44a4aeaf1f60a9. Upgrading the affected component is advised.

Severity

CVSS 4.0

5.5 medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P

CVSS 3.1

7.5 high
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS
0.7% (unchanged from 0.7% a week ago; 0.7% 30 days ago) estimated probability of exploitation activity in the next 30 days; 54th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: yes · Technical impact: partial, assessed 2026-10-02. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-404 Improper Resource Shutdown or Release
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-103241 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-103241?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-103241?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-103241 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
vllm:vllmthrough 0.26.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
PYSEC-2026-4186PyPIvllm<0.27.00.27.0

Red Hat

Red Hat rates this Important.

Red Hat's statement

An important impact denial of service flaw was found in the upstream vLLM project, in the Rust-based Gemma4UnifiedParser component (rust/src/parser/src/unified/gemma4.rs). The parser implements a hand-written recursive grammar without a recursion depth limit, so crafted input containing deeply nested structures, such as nested tool-call arguments in model output, drives unbounded recursion that exhausts a worker thread's stack and terminates the vLLM process. A remote attacker able to submit such manipulated input can cause the model-serving process to become unresponsive or crash, disrupting service for legitimate users; confidentiality and integrity are not affected. Multiple Red Hat AI products ship vulnerable versions of vLLM and are affected by this flaw.

Red Hat's mitigation

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

ProductPackageStateAdvisory
Red Hat AI Inference Serverrhaii-fast/vllm-cpu-rhel9Not affected
Red Hat AI Inference Serverrhaii-fast/vllm-cuda-rhel9Not affected
Red Hat AI Inference Serverrhaii-fast/vllm-gaudi-rhel9Affected
Red Hat AI Inference Serverrhaii-fast/vllm-neuron-rhel9Will not fix
Red Hat AI Inference Serverrhaii-fast/vllm-omni-cuda-rhel9Will not fix
Red Hat AI Inference Serverrhaii-fast/vllm-rocm-rhel9Not affected
Red Hat AI Inference Serverrhaii-fast/vllm-spyre-rhel9Not affected
Red Hat AI Inference Serverrhaii-fast/vllm-tpu-rhel9Not affected
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-cuda-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-rocm-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-spyre-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-tpu-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-aws-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-rocm-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gaudi-rhel9Affected
12 more in the JSON and on Red Hat's page.

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-103241.

Attack patterns (CAPEC)

  • CAPEC-125 Flooding Likelihood: High · Severity: Medium
  • CAPEC-130 Excessive Allocation Likelihood: Medium · Severity: Medium
  • CAPEC-131 Resource Leak Exposure Likelihood: Medium · Severity: Medium
  • CAPEC-494 TCP Fragmentation
  • CAPEC-495 UDP Fragmentation
  • CAPEC-496 ICMP Fragmentation
  • CAPEC-666 BlueSmacking Likelihood: Medium · Severity: Medium

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON